© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62422
    Prev
    Next
    INDEX
    Explanations

    citations, concept, ruins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    herits
    -0.09
     aka
    -0.08
    /ts
    -0.07
    tvr
    -0.07
    æ²ĥæĸ¯
    -0.07
     chi
    -0.07
    umm
    -0.07
    programma
    -0.07
    éĤ£ä¸ªæŶåĢĻ
    -0.07
    ivel
    -0.07
    POSITIVE LOGITS
    åı¯ä¸į
    0.07
    owl
    0.07
     Issue
    0.07
    azzi
    0.07
    ignored
    0.06
    åĽłæŃ¤åľ¨
    0.06
    éĹ®é¢ĺçļĦ
    0.06
    å¥½åľ¨
    0.06
    agne
    0.06
     neglected
    0.06
    Activations Density 0.049%

    No Known Activations